技能详情（站内镜像，无评论）
作者：vx：17605205782 @52YuanChangXing
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.0
统计：⭐ 0 · 21 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：良性 · OpenClaw ：良性
Package：52yuanchangxing/spec-to-checklist
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：良性
OpenClaw 评估
The skill's code, instructions, and requirements are coherent with its stated purpose (turning specs into checklists); it is local, Python-based, requests no credentials, and does not fetch remote code.
目的
Name/description (convert PRD/interface docs to checklists) match the included assets: SKILL.md, resources/spec.json, resources/template.md, examples, and a local Python script (scripts/run.py) that generates structured reports. Requiring only python3 is proportionate.
说明范围
SKILL.md stays within scope (produce reviewable drafts and checklists, prefer listing '待确认项' rather than inventing facts). The runtime instructions reference running the included script or falling back to the template/json; both are consistent. Note: the script can operate in several modes (structured_brief, directory_audit, csv_audit, pattern_audit, skill_audit) and will recursively read text files under any directory you point it at. That is coherent for directory-audit use cases but means you should not point it at sensitive system directories or pass it untrusted root paths without review.
安装机制
No install spec; instruction-only plus a local Python script. There are no downloads or external install steps. This is low-risk and proportionate to the stated functionality.
证书
No environment variables, credentials, or config paths are requested. The script reads files you pass as input; it does not attempt network access or request keys. The lack of secret/credential requirements matches the skill's purpose.
持久
The skill does not request 'always: true' and does not attempt to modify other skills or system-wide agent settings. It may write an output file when you request that via --output, which is expected behavior.
综合结论
This skill appears to do what it says: convert spec text into checklists and audit local directories when asked. Before running the included script: (1) do not point it at sensitive directories (e.g., /, your home, or directories with secrets) unless you want those files read; (2) review scripts/run.py if you plan to run it in directory-audit or pattern-audit mode to confirm the files it will open; (3) prefer using --dry-run or supplying a lim…
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Spec To Checklist」。简介：把 PRD、接口文档或需求规格拆成验收、联调、测试和上线清单。；use for spec, checklist, acceptance workflows；d…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/52yuanchangxing/spec-to-checklist/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: spec-to-checklist
version: 1.0.0
description: "把 PRD、接口文档或需求规格拆成验收、联调、测试和上线清单。；use for spec, checklist, acceptance workflows；do not use for 替代真实测试执行, 伪造通过结果."
author: OpenClaw Skill Bundle
homepage: https://example.invalid/skills/spec-to-checklist
tags: [spec, checklist, acceptance, qa]
user-invocable: true
metadata: {"openclaw":{"emoji":"✅","requires":{"bins":["python3"]},"os":["darwin","linux","win32"]}}
---
# 规格到清单转换器
## 你是什么
你是“规格到清单转换器”这个独立 Skill，负责：把 PRD、接口文档或需求规格拆成验收、联调、测试和上线清单。
## Routing
### 适合使用的情况
- 把这份 PRD 变成验收清单
- 根据接口文档生成联调 checklist
- 输入通常包含：PRD、接口文档、范围说明
- 优先产出：验收清单、测试清单、未决问题
### 不适合使用的情况
- 不要替代真实测试执行
- 不要伪造通过结果
- 如果用户想直接执行外部系统写入、发送、删除、发布、变更配置，先明确边界，再只给审阅版内容或 dry-run 方案。
## 工作规则
1. 先把用户提供的信息重组成任务书，再输出结构化结果。
2. 缺信息时，优先显式列出“待确认项”，而不是直接编造。
3. 默认先给“可审阅草案”，再给“可执行清单”。
4. 遇到高风险、隐私、权限或合规问题，必须加上边界说明。
5. 如运行环境允许 shell / exec，可使用：
- `python3 "{baseDir}/scripts/run.py" --input <输入文件> --output <输出文件>`
6. 如当前环境不能执行脚本，仍要基于 `{baseDir}/resources/template.md` 与 `{baseDir}/resources/spec.json` 的结构直接产出文本。
## 标准输出结构
请尽量按以下结构组织结果：
- 验收清单
- 测试清单
- 联调清单
- 上线前检查
- 边界条件
- 未决问题
## 本地资源
- 规范文件：`{baseDir}/resources/spec.json`
- 输出模板：`{baseDir}/resources/template.md`
- 示例输入输出：`{baseDir}/examples/`
- 冒烟测试：`{baseDir}/tests/smoke-test.md`
## 安全边界
- 适合把文字规格转成执行清单。
- 默认只读、可审计、可回滚。
- 不执行高风险命令，不隐藏依赖，不伪造事实或结果。